-
- 
+
+ 
+
NextChat (ChatGPT Next Web)
English / [简体中文](./README_CN.md)
-One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4 & Gemini Pro support.
+One-Click to get a well-designed cross-platform ChatGPT web UI, with Claude, GPT4 & Gemini Pro support.
-一键免费部署你的跨平台私人 ChatGPT 应用, 支持 GPT3, GPT4 & Gemini Pro 模型。
+一键免费部署你的跨平台私人 ChatGPT 应用, 支持 Claude, GPT4 & Gemini Pro 模型。
[![Saas][Saas-image]][saas-url]
[![Web][Web-image]][web-url]
@@ -18,9 +19,9 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4
[![MacOS][MacOS-image]][download-url]
[![Linux][Linux-image]][download-url]
-[NextChatAI](https://nextchat.dev/chat?utm_source=readme) / [Web App](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Discord](https://discord.gg/YCkeafCafC) / [Enterprise Edition](#enterprise-edition) / [Twitter](https://twitter.com/NextChatDev)
+[NextChatAI](https://nextchat.dev/chat?utm_source=readme) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Discord](https://discord.gg/YCkeafCafC) / [Enterprise Edition](#enterprise-edition) / [Twitter](https://twitter.com/NextChatDev)
-[NextChatAI](https://nextchat.dev/chat) / [网页版](https://app.nextchat.dev) / [客户端](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) / [反馈](https://github.com/Yidadaa/ChatGPT-Next-Web/issues)
+[NextChatAI](https://nextchat.dev/chat) / [自部署网页版](https://app.nextchat.dev) / [客户端](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [企业版](#%E4%BC%81%E4%B8%9A%E7%89%88) / [反馈](https://github.com/Yidadaa/ChatGPT-Next-Web/issues)
[saas-url]: https://nextchat.dev/chat?utm_source=readme
[saas-image]: https://img.shields.io/badge/NextChat-Saas-green?logo=microsoftedge
@@ -31,7 +32,7 @@ One-Click to get a well-designed cross-platform ChatGPT web UI, with GPT3, GPT4
[MacOS-image]: https://img.shields.io/badge/-MacOS-black?logo=apple
[Linux-image]: https://img.shields.io/badge/-Linux-333?logo=ubuntu
-[
](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [
](https://zeabur.com/templates/ZBUEFA) [
](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [
](https://www.bt.cn/new/download.html) [
](https://computenest.aliyun.com/market/service-f1c9b75e59814dc49d52)
+[
](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FChatGPTNextWeb%2FChatGPT-Next-Web&env=OPENAI_API_KEY&env=CODE&project-name=nextchat&repository-name=NextChat) [
](https://zeabur.com/templates/ZBUEFA) [
](https://gitpod.io/#https://github.com/Yidadaa/ChatGPT-Next-Web) [
](https://www.bt.cn/new/download.html)
[
](https://monica.im/?utm=nxcrp)
diff --git a/app/api/[provider]/[...path]/route.ts b/app/api/[provider]/[...path]/route.ts
index 3017fd371..3b5833d7e 100644
--- a/app/api/[provider]/[...path]/route.ts
+++ b/app/api/[provider]/[...path]/route.ts
@@ -10,6 +10,7 @@ import { handle as alibabaHandler } from "../../alibaba";
import { handle as moonshotHandler } from "../../moonshot";
import { handle as stabilityHandler } from "../../stability";
import { handle as iflytekHandler } from "../../iflytek";
+import { handle as deepseekHandler } from "../../deepseek";
import { handle as xaiHandler } from "../../xai";
import { handle as chatglmHandler } from "../../glm";
import { handle as proxyHandler } from "../../proxy";
@@ -40,6 +41,8 @@ async function handle(
return stabilityHandler(req, { params });
case ApiPath.Iflytek:
return iflytekHandler(req, { params });
+ case ApiPath.DeepSeek:
+ return deepseekHandler(req, { params });
case ApiPath.XAI:
return xaiHandler(req, { params });
case ApiPath.ChatGLM:
diff --git a/app/api/alibaba.ts b/app/api/alibaba.ts
index 894b1ae4c..20f6caefa 100644
--- a/app/api/alibaba.ts
+++ b/app/api/alibaba.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
const serverConfig = getServerSideConfig();
@@ -89,7 +89,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.Alibaba as string,
diff --git a/app/api/anthropic.ts b/app/api/anthropic.ts
index 7a4444371..b96637b2c 100644
--- a/app/api/anthropic.ts
+++ b/app/api/anthropic.ts
@@ -9,7 +9,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "./auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare";
const ALLOWD_PATH = new Set([Anthropic.ChatPath, Anthropic.ChatPath1]);
@@ -122,7 +122,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.Anthropic as string,
diff --git a/app/api/auth.ts b/app/api/auth.ts
index 6703b64bd..1760c249c 100644
--- a/app/api/auth.ts
+++ b/app/api/auth.ts
@@ -92,6 +92,9 @@ export function auth(req: NextRequest, modelProvider: ModelProvider) {
systemApiKey =
serverConfig.iflytekApiKey + ":" + serverConfig.iflytekApiSecret;
break;
+ case ModelProvider.DeepSeek:
+ systemApiKey = serverConfig.deepseekApiKey;
+ break;
case ModelProvider.XAI:
systemApiKey = serverConfig.xaiApiKey;
break;
diff --git a/app/api/baidu.ts b/app/api/baidu.ts
index 0408b43c5..0f4e05ee8 100644
--- a/app/api/baidu.ts
+++ b/app/api/baidu.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
import { getAccessToken } from "@/app/utils/baidu";
const serverConfig = getServerSideConfig();
@@ -104,7 +104,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.Baidu as string,
diff --git a/app/api/bytedance.ts b/app/api/bytedance.ts
index cb65b1061..51b39ceb7 100644
--- a/app/api/bytedance.ts
+++ b/app/api/bytedance.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
const serverConfig = getServerSideConfig();
@@ -88,7 +88,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.ByteDance as string,
diff --git a/app/api/common.ts b/app/api/common.ts
index 495a12ccd..b7e41fa26 100644
--- a/app/api/common.ts
+++ b/app/api/common.ts
@@ -2,7 +2,7 @@ import { NextRequest, NextResponse } from "next/server";
import { getServerSideConfig } from "../config/server";
import { OPENAI_BASE_URL, ServiceProvider } from "../constant";
import { cloudflareAIGatewayUrl } from "../utils/cloudflare";
-import { getModelProvider, isModelAvailableInServer } from "../utils/model";
+import { getModelProvider, isModelNotavailableInServer } from "../utils/model";
const serverConfig = getServerSideConfig();
@@ -118,15 +118,14 @@ export async function requestOpenai(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
- ServiceProvider.OpenAI as string,
- ) ||
- isModelAvailableInServer(
- serverConfig.customModels,
- jsonBody?.model as string,
- ServiceProvider.Azure as string,
+ [
+ ServiceProvider.OpenAI,
+ ServiceProvider.Azure,
+ jsonBody?.model as string, // support provider-unspecified model
+ ],
)
) {
return NextResponse.json(
diff --git a/app/api/deepseek.ts b/app/api/deepseek.ts
new file mode 100644
index 000000000..06d97a0d6
--- /dev/null
+++ b/app/api/deepseek.ts
@@ -0,0 +1,128 @@
+import { getServerSideConfig } from "@/app/config/server";
+import {
+ DEEPSEEK_BASE_URL,
+ ApiPath,
+ ModelProvider,
+ ServiceProvider,
+} from "@/app/constant";
+import { prettyObject } from "@/app/utils/format";
+import { NextRequest, NextResponse } from "next/server";
+import { auth } from "@/app/api/auth";
+import { isModelNotavailableInServer } from "@/app/utils/model";
+
+const serverConfig = getServerSideConfig();
+
+export async function handle(
+ req: NextRequest,
+ { params }: { params: { path: string[] } },
+) {
+ console.log("[DeepSeek Route] params ", params);
+
+ if (req.method === "OPTIONS") {
+ return NextResponse.json({ body: "OK" }, { status: 200 });
+ }
+
+ const authResult = auth(req, ModelProvider.DeepSeek);
+ if (authResult.error) {
+ return NextResponse.json(authResult, {
+ status: 401,
+ });
+ }
+
+ try {
+ const response = await request(req);
+ return response;
+ } catch (e) {
+ console.error("[DeepSeek] ", e);
+ return NextResponse.json(prettyObject(e));
+ }
+}
+
+async function request(req: NextRequest) {
+ const controller = new AbortController();
+
+ // alibaba use base url or just remove the path
+ let path = `${req.nextUrl.pathname}`.replaceAll(ApiPath.DeepSeek, "");
+
+ let baseUrl = serverConfig.deepseekUrl || DEEPSEEK_BASE_URL;
+
+ if (!baseUrl.startsWith("http")) {
+ baseUrl = `https://${baseUrl}`;
+ }
+
+ if (baseUrl.endsWith("/")) {
+ baseUrl = baseUrl.slice(0, -1);
+ }
+
+ console.log("[Proxy] ", path);
+ console.log("[Base Url]", baseUrl);
+
+ const timeoutId = setTimeout(
+ () => {
+ controller.abort();
+ },
+ 10 * 60 * 1000,
+ );
+
+ const fetchUrl = `${baseUrl}${path}`;
+ const fetchOptions: RequestInit = {
+ headers: {
+ "Content-Type": "application/json",
+ Authorization: req.headers.get("Authorization") ?? "",
+ },
+ method: req.method,
+ body: req.body,
+ redirect: "manual",
+ // @ts-ignore
+ duplex: "half",
+ signal: controller.signal,
+ };
+
+ // #1815 try to refuse some request to some models
+ if (serverConfig.customModels && req.body) {
+ try {
+ const clonedBody = await req.text();
+ fetchOptions.body = clonedBody;
+
+ const jsonBody = JSON.parse(clonedBody) as { model?: string };
+
+ // not undefined and is false
+ if (
+ isModelNotavailableInServer(
+ serverConfig.customModels,
+ jsonBody?.model as string,
+ ServiceProvider.Moonshot as string,
+ )
+ ) {
+ return NextResponse.json(
+ {
+ error: true,
+ message: `you are not allowed to use ${jsonBody?.model} model`,
+ },
+ {
+ status: 403,
+ },
+ );
+ }
+ } catch (e) {
+ console.error(`[DeepSeek] filter`, e);
+ }
+ }
+ try {
+ const res = await fetch(fetchUrl, fetchOptions);
+
+ // to prevent browser prompt for credentials
+ const newHeaders = new Headers(res.headers);
+ newHeaders.delete("www-authenticate");
+ // to disable nginx buffering
+ newHeaders.set("X-Accel-Buffering", "no");
+
+ return new Response(res.body, {
+ status: res.status,
+ statusText: res.statusText,
+ headers: newHeaders,
+ });
+ } finally {
+ clearTimeout(timeoutId);
+ }
+}
diff --git a/app/api/glm.ts b/app/api/glm.ts
index 3625b9f7b..8431c5db5 100644
--- a/app/api/glm.ts
+++ b/app/api/glm.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
const serverConfig = getServerSideConfig();
@@ -89,7 +89,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.ChatGLM as string,
diff --git a/app/api/iflytek.ts b/app/api/iflytek.ts
index 8b8227dce..6624f74e9 100644
--- a/app/api/iflytek.ts
+++ b/app/api/iflytek.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
// iflytek
const serverConfig = getServerSideConfig();
@@ -89,7 +89,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.Iflytek as string,
diff --git a/app/api/moonshot.ts b/app/api/moonshot.ts
index 5bf4807e3..792d14d33 100644
--- a/app/api/moonshot.ts
+++ b/app/api/moonshot.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
const serverConfig = getServerSideConfig();
@@ -88,7 +88,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.Moonshot as string,
diff --git a/app/api/xai.ts b/app/api/xai.ts
index a4ee8b397..4aad5e5fb 100644
--- a/app/api/xai.ts
+++ b/app/api/xai.ts
@@ -8,7 +8,7 @@ import {
import { prettyObject } from "@/app/utils/format";
import { NextRequest, NextResponse } from "next/server";
import { auth } from "@/app/api/auth";
-import { isModelAvailableInServer } from "@/app/utils/model";
+import { isModelNotavailableInServer } from "@/app/utils/model";
const serverConfig = getServerSideConfig();
@@ -88,7 +88,7 @@ async function request(req: NextRequest) {
// not undefined and is false
if (
- isModelAvailableInServer(
+ isModelNotavailableInServer(
serverConfig.customModels,
jsonBody?.model as string,
ServiceProvider.XAI as string,
diff --git a/app/client/api.ts b/app/client/api.ts
index 1da81e964..8f263763b 100644
--- a/app/client/api.ts
+++ b/app/client/api.ts
@@ -20,6 +20,7 @@ import { QwenApi } from "./platforms/alibaba";
import { HunyuanApi } from "./platforms/tencent";
import { MoonshotApi } from "./platforms/moonshot";
import { SparkApi } from "./platforms/iflytek";
+import { DeepSeekApi } from "./platforms/deepseek";
import { XAIApi } from "./platforms/xai";
import { ChatGLMApi } from "./platforms/glm";
@@ -154,6 +155,9 @@ export class ClientApi {
case ModelProvider.Iflytek:
this.llm = new SparkApi();
break;
+ case ModelProvider.DeepSeek:
+ this.llm = new DeepSeekApi();
+ break;
case ModelProvider.XAI:
this.llm = new XAIApi();
break;
@@ -247,6 +251,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
const isAlibaba = modelConfig.providerName === ServiceProvider.Alibaba;
const isMoonshot = modelConfig.providerName === ServiceProvider.Moonshot;
const isIflytek = modelConfig.providerName === ServiceProvider.Iflytek;
+ const isDeepSeek = modelConfig.providerName === ServiceProvider.DeepSeek;
const isXAI = modelConfig.providerName === ServiceProvider.XAI;
const isChatGLM = modelConfig.providerName === ServiceProvider.ChatGLM;
const isEnabledAccessControl = accessStore.enabledAccessControl();
@@ -264,6 +269,8 @@ export function getHeaders(ignoreHeaders: boolean = false) {
? accessStore.moonshotApiKey
: isXAI
? accessStore.xaiApiKey
+ : isDeepSeek
+ ? accessStore.deepseekApiKey
: isChatGLM
? accessStore.chatglmApiKey
: isIflytek
@@ -280,6 +287,7 @@ export function getHeaders(ignoreHeaders: boolean = false) {
isAlibaba,
isMoonshot,
isIflytek,
+ isDeepSeek,
isXAI,
isChatGLM,
apiKey,
@@ -302,6 +310,13 @@ export function getHeaders(ignoreHeaders: boolean = false) {
isAzure,
isAnthropic,
isBaidu,
+ isByteDance,
+ isAlibaba,
+ isMoonshot,
+ isIflytek,
+ isDeepSeek,
+ isXAI,
+ isChatGLM,
apiKey,
isEnabledAccessControl,
} = getConfig();
@@ -344,6 +359,8 @@ export function getClientApi(provider: ServiceProvider): ClientApi {
return new ClientApi(ModelProvider.Moonshot);
case ServiceProvider.Iflytek:
return new ClientApi(ModelProvider.Iflytek);
+ case ServiceProvider.DeepSeek:
+ return new ClientApi(ModelProvider.DeepSeek);
case ServiceProvider.XAI:
return new ClientApi(ModelProvider.XAI);
case ServiceProvider.ChatGLM:
diff --git a/app/client/platforms/deepseek.ts b/app/client/platforms/deepseek.ts
new file mode 100644
index 000000000..28f15a435
--- /dev/null
+++ b/app/client/platforms/deepseek.ts
@@ -0,0 +1,200 @@
+"use client";
+// azure and openai, using same models. so using same LLMApi.
+import {
+ ApiPath,
+ DEEPSEEK_BASE_URL,
+ DeepSeek,
+ REQUEST_TIMEOUT_MS,
+} from "@/app/constant";
+import {
+ useAccessStore,
+ useAppConfig,
+ useChatStore,
+ ChatMessageTool,
+ usePluginStore,
+} from "@/app/store";
+import { stream } from "@/app/utils/chat";
+import {
+ ChatOptions,
+ getHeaders,
+ LLMApi,
+ LLMModel,
+ SpeechOptions,
+} from "../api";
+import { getClientConfig } from "@/app/config/client";
+import { getMessageTextContent } from "@/app/utils";
+import { RequestPayload } from "./openai";
+import { fetch } from "@/app/utils/stream";
+
+export class DeepSeekApi implements LLMApi {
+ private disableListModels = true;
+
+ path(path: string): string {
+ const accessStore = useAccessStore.getState();
+
+ let baseUrl = "";
+
+ if (accessStore.useCustomConfig) {
+ baseUrl = accessStore.moonshotUrl;
+ }
+
+ if (baseUrl.length === 0) {
+ const isApp = !!getClientConfig()?.isApp;
+ const apiPath = ApiPath.DeepSeek;
+ baseUrl = isApp ? DEEPSEEK_BASE_URL : apiPath;
+ }
+
+ if (baseUrl.endsWith("/")) {
+ baseUrl = baseUrl.slice(0, baseUrl.length - 1);
+ }
+ if (!baseUrl.startsWith("http") && !baseUrl.startsWith(ApiPath.DeepSeek)) {
+ baseUrl = "https://" + baseUrl;
+ }
+
+ console.log("[Proxy Endpoint] ", baseUrl, path);
+
+ return [baseUrl, path].join("/");
+ }
+
+ extractMessage(res: any) {
+ return res.choices?.at(0)?.message?.content ?? "";
+ }
+
+ speech(options: SpeechOptions): Promise
{
+ throw new Error("Method not implemented.");
+ }
+
+ async chat(options: ChatOptions) {
+ const messages: ChatOptions["messages"] = [];
+ for (const v of options.messages) {
+ const content = getMessageTextContent(v);
+ messages.push({ role: v.role, content });
+ }
+
+ const modelConfig = {
+ ...useAppConfig.getState().modelConfig,
+ ...useChatStore.getState().currentSession().mask.modelConfig,
+ ...{
+ model: options.config.model,
+ providerName: options.config.providerName,
+ },
+ };
+
+ const requestPayload: RequestPayload = {
+ messages,
+ stream: options.config.stream,
+ model: modelConfig.model,
+ temperature: modelConfig.temperature,
+ presence_penalty: modelConfig.presence_penalty,
+ frequency_penalty: modelConfig.frequency_penalty,
+ top_p: modelConfig.top_p,
+ // max_tokens: Math.max(modelConfig.max_tokens, 1024),
+ // Please do not ask me why not send max_tokens, no reason, this param is just shit, I dont want to explain anymore.
+ };
+
+ console.log("[Request] openai payload: ", requestPayload);
+
+ const shouldStream = !!options.config.stream;
+ const controller = new AbortController();
+ options.onController?.(controller);
+
+ try {
+ const chatPath = this.path(DeepSeek.ChatPath);
+ const chatPayload = {
+ method: "POST",
+ body: JSON.stringify(requestPayload),
+ signal: controller.signal,
+ headers: getHeaders(),
+ };
+
+ // make a fetch request
+ const requestTimeoutId = setTimeout(
+ () => controller.abort(),
+ REQUEST_TIMEOUT_MS,
+ );
+
+ if (shouldStream) {
+ const [tools, funcs] = usePluginStore
+ .getState()
+ .getAsTools(
+ useChatStore.getState().currentSession().mask?.plugin || [],
+ );
+ return stream(
+ chatPath,
+ requestPayload,
+ getHeaders(),
+ tools as any,
+ funcs,
+ controller,
+ // parseSSE
+ (text: string, runTools: ChatMessageTool[]) => {
+ // console.log("parseSSE", text, runTools);
+ const json = JSON.parse(text);
+ const choices = json.choices as Array<{
+ delta: {
+ content: string;
+ tool_calls: ChatMessageTool[];
+ };
+ }>;
+ const tool_calls = choices[0]?.delta?.tool_calls;
+ if (tool_calls?.length > 0) {
+ const index = tool_calls[0]?.index;
+ const id = tool_calls[0]?.id;
+ const args = tool_calls[0]?.function?.arguments;
+ if (id) {
+ runTools.push({
+ id,
+ type: tool_calls[0]?.type,
+ function: {
+ name: tool_calls[0]?.function?.name as string,
+ arguments: args,
+ },
+ });
+ } else {
+ // @ts-ignore
+ runTools[index]["function"]["arguments"] += args;
+ }
+ }
+ return choices[0]?.delta?.content;
+ },
+ // processToolMessage, include tool_calls message and tool call results
+ (
+ requestPayload: RequestPayload,
+ toolCallMessage: any,
+ toolCallResult: any[],
+ ) => {
+ // @ts-ignore
+ requestPayload?.messages?.splice(
+ // @ts-ignore
+ requestPayload?.messages?.length,
+ 0,
+ toolCallMessage,
+ ...toolCallResult,
+ );
+ },
+ options,
+ );
+ } else {
+ const res = await fetch(chatPath, chatPayload);
+ clearTimeout(requestTimeoutId);
+
+ const resJson = await res.json();
+ const message = this.extractMessage(resJson);
+ options.onFinish(message, res);
+ }
+ } catch (e) {
+ console.log("[Request] failed to make a chat request", e);
+ options.onError?.(e as Error);
+ }
+ }
+ async usage() {
+ return {
+ used: 0,
+ total: 0,
+ };
+ }
+
+ async models(): Promise {
+ return [];
+ }
+}
diff --git a/app/client/platforms/glm.ts b/app/client/platforms/glm.ts
index a7965947f..a8d1869e3 100644
--- a/app/client/platforms/glm.ts
+++ b/app/client/platforms/glm.ts
@@ -21,16 +21,108 @@ import {
SpeechOptions,
} from "../api";
import { getClientConfig } from "@/app/config/client";
-import { getMessageTextContent } from "@/app/utils";
+import { getMessageTextContent, isVisionModel } from "@/app/utils";
import { RequestPayload } from "./openai";
import { fetch } from "@/app/utils/stream";
+import { preProcessImageContent } from "@/app/utils/chat";
+
+interface BasePayload {
+ model: string;
+}
+
+interface ChatPayload extends BasePayload {
+ messages: ChatOptions["messages"];
+ stream?: boolean;
+ temperature?: number;
+ presence_penalty?: number;
+ frequency_penalty?: number;
+ top_p?: number;
+}
+
+interface ImageGenerationPayload extends BasePayload {
+ prompt: string;
+ size?: string;
+ user_id?: string;
+}
+
+interface VideoGenerationPayload extends BasePayload {
+ prompt: string;
+ duration?: number;
+ resolution?: string;
+ user_id?: string;
+}
+
+type ModelType = "chat" | "image" | "video";
export class ChatGLMApi implements LLMApi {
private disableListModels = true;
+ private getModelType(model: string): ModelType {
+ if (model.startsWith("cogview-")) return "image";
+ if (model.startsWith("cogvideo-")) return "video";
+ return "chat";
+ }
+
+ private getModelPath(type: ModelType): string {
+ switch (type) {
+ case "image":
+ return ChatGLM.ImagePath;
+ case "video":
+ return ChatGLM.VideoPath;
+ default:
+ return ChatGLM.ChatPath;
+ }
+ }
+
+ private createPayload(
+ messages: ChatOptions["messages"],
+ modelConfig: any,
+ options: ChatOptions,
+ ): BasePayload {
+ const modelType = this.getModelType(modelConfig.model);
+ const lastMessage = messages[messages.length - 1];
+ const prompt =
+ typeof lastMessage.content === "string"
+ ? lastMessage.content
+ : lastMessage.content.map((c) => c.text).join("\n");
+
+ switch (modelType) {
+ case "image":
+ return {
+ model: modelConfig.model,
+ prompt,
+ size: options.config.size,
+ } as ImageGenerationPayload;
+ default:
+ return {
+ messages,
+ stream: options.config.stream,
+ model: modelConfig.model,
+ temperature: modelConfig.temperature,
+ presence_penalty: modelConfig.presence_penalty,
+ frequency_penalty: modelConfig.frequency_penalty,
+ top_p: modelConfig.top_p,
+ } as ChatPayload;
+ }
+ }
+
+ private parseResponse(modelType: ModelType, json: any): string {
+ switch (modelType) {
+ case "image": {
+ const imageUrl = json.data?.[0]?.url;
+ return imageUrl ? `` : "";
+ }
+ case "video": {
+ const videoUrl = json.data?.[0]?.url;
+ return videoUrl ? `` : "";
+ }
+ default:
+ return this.extractMessage(json);
+ }
+ }
+
path(path: string): string {
const accessStore = useAccessStore.getState();
-
let baseUrl = "";
if (accessStore.useCustomConfig) {
@@ -51,7 +143,6 @@ export class ChatGLMApi implements LLMApi {
}
console.log("[Proxy Endpoint] ", baseUrl, path);
-
return [baseUrl, path].join("/");
}
@@ -64,9 +155,12 @@ export class ChatGLMApi implements LLMApi {
}
async chat(options: ChatOptions) {
+ const visionModel = isVisionModel(options.config.model);
const messages: ChatOptions["messages"] = [];
for (const v of options.messages) {
- const content = getMessageTextContent(v);
+ const content = visionModel
+ ? await preProcessImageContent(v.content)
+ : getMessageTextContent(v);
messages.push({ role: v.role, content });
}
@@ -78,25 +172,16 @@ export class ChatGLMApi implements LLMApi {
providerName: options.config.providerName,
},
};
+ const modelType = this.getModelType(modelConfig.model);
+ const requestPayload = this.createPayload(messages, modelConfig, options);
+ const path = this.path(this.getModelPath(modelType));
- const requestPayload: RequestPayload = {
- messages,
- stream: options.config.stream,
- model: modelConfig.model,
- temperature: modelConfig.temperature,
- presence_penalty: modelConfig.presence_penalty,
- frequency_penalty: modelConfig.frequency_penalty,
- top_p: modelConfig.top_p,
- };
+ console.log(`[Request] glm ${modelType} payload: `, requestPayload);
- console.log("[Request] glm payload: ", requestPayload);
-
- const shouldStream = !!options.config.stream;
const controller = new AbortController();
options.onController?.(controller);
try {
- const chatPath = this.path(ChatGLM.ChatPath);
const chatPayload = {
method: "POST",
body: JSON.stringify(requestPayload),
@@ -104,12 +189,23 @@ export class ChatGLMApi implements LLMApi {
headers: getHeaders(),
};
- // make a fetch request
const requestTimeoutId = setTimeout(
() => controller.abort(),
REQUEST_TIMEOUT_MS,
);
+ if (modelType === "image" || modelType === "video") {
+ const res = await fetch(path, chatPayload);
+ clearTimeout(requestTimeoutId);
+
+ const resJson = await res.json();
+ console.log(`[Response] glm ${modelType}:`, resJson);
+ const message = this.parseResponse(modelType, resJson);
+ options.onFinish(message, res);
+ return;
+ }
+
+ const shouldStream = !!options.config.stream;
if (shouldStream) {
const [tools, funcs] = usePluginStore
.getState()
@@ -117,7 +213,7 @@ export class ChatGLMApi implements LLMApi {
useChatStore.getState().currentSession().mask?.plugin || [],
);
return stream(
- chatPath,
+ path,
requestPayload,
getHeaders(),
tools as any,
@@ -125,7 +221,6 @@ export class ChatGLMApi implements LLMApi {
controller,
// parseSSE
(text: string, runTools: ChatMessageTool[]) => {
- // console.log("parseSSE", text, runTools);
const json = JSON.parse(text);
const choices = json.choices as Array<{
delta: {
@@ -154,7 +249,7 @@ export class ChatGLMApi implements LLMApi {
}
return choices[0]?.delta?.content;
},
- // processToolMessage, include tool_calls message and tool call results
+ // processToolMessage
(
requestPayload: RequestPayload,
toolCallMessage: any,
@@ -172,7 +267,7 @@ export class ChatGLMApi implements LLMApi {
options,
);
} else {
- const res = await fetch(chatPath, chatPayload);
+ const res = await fetch(path, chatPayload);
clearTimeout(requestTimeoutId);
const resJson = await res.json();
@@ -184,6 +279,7 @@ export class ChatGLMApi implements LLMApi {
options.onError?.(e as Error);
}
}
+
async usage() {
return {
used: 0,
diff --git a/app/client/platforms/google.ts b/app/client/platforms/google.ts
index a7bce4fc2..5ca8e1071 100644
--- a/app/client/platforms/google.ts
+++ b/app/client/platforms/google.ts
@@ -60,9 +60,18 @@ export class GeminiProApi implements LLMApi {
extractMessage(res: any) {
console.log("[Response] gemini-pro response: ", res);
+ const getTextFromParts = (parts: any[]) => {
+ if (!Array.isArray(parts)) return "";
+
+ return parts
+ .map((part) => part?.text || "")
+ .filter((text) => text.trim() !== "")
+ .join("\n\n");
+ };
+
return (
- res?.candidates?.at(0)?.content?.parts.at(0)?.text ||
- res?.at(0)?.candidates?.at(0)?.content?.parts.at(0)?.text ||
+ getTextFromParts(res?.candidates?.at(0)?.content?.parts) ||
+ getTextFromParts(res?.at(0)?.candidates?.at(0)?.content?.parts) ||
res?.error?.message ||
""
);
@@ -223,7 +232,10 @@ export class GeminiProApi implements LLMApi {
},
});
}
- return chunkJson?.candidates?.at(0)?.content.parts.at(0)?.text;
+ return chunkJson?.candidates
+ ?.at(0)
+ ?.content.parts?.map((part: { text: string }) => part.text)
+ .join("\n\n");
},
// processToolMessage, include tool_calls message and tool call results
(
diff --git a/app/client/platforms/openai.ts b/app/client/platforms/openai.ts
index 15cfb7ca6..5a110b84b 100644
--- a/app/client/platforms/openai.ts
+++ b/app/client/platforms/openai.ts
@@ -24,7 +24,7 @@ import {
stream,
} from "@/app/utils/chat";
import { cloudflareAIGatewayUrl } from "@/app/utils/cloudflare";
-import { DalleSize, DalleQuality, DalleStyle } from "@/app/typing";
+import { ModelSize, DalleQuality, DalleStyle } from "@/app/typing";
import {
ChatOptions,
@@ -73,7 +73,7 @@ export interface DalleRequestPayload {
prompt: string;
response_format: "url" | "b64_json";
n: number;
- size: DalleSize;
+ size: ModelSize;
quality: DalleQuality;
style: DalleStyle;
}
diff --git a/app/components/chat.tsx b/app/components/chat.tsx
index 51fe74fe7..f34f7d78e 100644
--- a/app/components/chat.tsx
+++ b/app/components/chat.tsx
@@ -72,6 +72,8 @@ import {
isDalle3,
showPlugins,
safeLocalStorage,
+ getModelSizes,
+ supportsCustomSize,
} from "../utils";
import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
@@ -79,7 +81,7 @@ import { uploadImage as uploadImageRemote } from "@/app/utils/chat";
import dynamic from "next/dynamic";
import { ChatControllerPool } from "../client/controller";
-import { DalleSize, DalleQuality, DalleStyle } from "../typing";
+import { DalleQuality, DalleStyle, ModelSize } from "../typing";
import { Prompt, usePromptStore } from "../store/prompt";
import Locale from "../locales";
@@ -519,10 +521,11 @@ export function ChatActions(props: {
const [showSizeSelector, setShowSizeSelector] = useState(false);
const [showQualitySelector, setShowQualitySelector] = useState(false);
const [showStyleSelector, setShowStyleSelector] = useState(false);
- const dalle3Sizes: DalleSize[] = ["1024x1024", "1792x1024", "1024x1792"];
+ const modelSizes = getModelSizes(currentModel);
const dalle3Qualitys: DalleQuality[] = ["standard", "hd"];
const dalle3Styles: DalleStyle[] = ["vivid", "natural"];
- const currentSize = session.mask.modelConfig?.size ?? "1024x1024";
+ const currentSize =
+ session.mask.modelConfig?.size ?? ("1024x1024" as ModelSize);
const currentQuality = session.mask.modelConfig?.quality ?? "standard";
const currentStyle = session.mask.modelConfig?.style ?? "vivid";
@@ -673,7 +676,7 @@ export function ChatActions(props: {
/>
)}
- {isDalle3(currentModel) && (
+ {supportsCustomSize(currentModel) && (
setShowSizeSelector(true)}
text={currentSize}
@@ -684,7 +687,7 @@ export function ChatActions(props: {
{showSizeSelector && (
({
+ items={modelSizes.map((m) => ({
title: m,
value: m,
}))}
diff --git a/app/components/sidebar.tsx b/app/components/sidebar.tsx
index a5e33b15e..fa4caee0d 100644
--- a/app/components/sidebar.tsx
+++ b/app/components/sidebar.tsx
@@ -22,7 +22,6 @@ import {
MIN_SIDEBAR_WIDTH,
NARROW_SIDEBAR_WIDTH,
Path,
- PLUGINS,
REPO_URL,
} from "../constant";
@@ -32,6 +31,12 @@ import dynamic from "next/dynamic";
import { showConfirm, Selector } from "./ui-lib";
import clsx from "clsx";
+const DISCOVERY = [
+ { name: Locale.Plugin.Name, path: Path.Plugins },
+ { name: "Stable Diffusion", path: Path.Sd },
+ { name: Locale.SearchChat.Page.Title, path: Path.SearchChat },
+];
+
const ChatList = dynamic(async () => (await import("./chat-list")).ChatList, {
loading: () => null,
});
@@ -219,7 +224,7 @@ export function SideBarTail(props: {
export function SideBar(props: { className?: string }) {
useHotKey();
const { onDragStart, shouldNarrow } = useDragSideBar();
- const [showPluginSelector, setShowPluginSelector] = useState(false);
+ const [showDiscoverySelector, setshowDiscoverySelector] = useState(false);
const navigate = useNavigate();
const config = useAppConfig();
const chatStore = useChatStore();
@@ -254,21 +259,21 @@ export function SideBar(props: { className?: string }) {
icon={}
text={shouldNarrow ? undefined : Locale.Discovery.Name}
className={styles["sidebar-bar-button"]}
- onClick={() => setShowPluginSelector(true)}
+ onClick={() => setshowDiscoverySelector(true)}
shadow
/>